Choose Your Own Adventure: Non-Linear AI-Assisted Programming with EvoGraph

TL;DR

EvoGraph is an IDE plugin that visualizes AI-assisted programming as an interactive graph, helping developers explore, compare, and manage AI-generated code changes more effectively.

Contribution

The paper introduces EvoGraph, a novel tool that records and visualizes AI-assisted coding history as a branching graph to improve developer control and understanding.

Findings

EvoGraph reduced cognitive load for developers.

Participants used the graph to explore and compare AI-generated code effectively.

The tool supported safe exploration and efficient iteration in AI-assisted programming.

Abstract

Current AI-assisted programming tools are predominantly linear and chat-based, which deviates from the iterative and branching nature of programming itself. Our preliminary study with developers using AI assistants suggested that they often struggle to explore alternatives, manage prompting sequences, and trace changes. Informed by these insights, we created EvoGraph, an IDE plugin that integrates AI interactions and code changes as a lightweight and interactive development graph. EvoGraph automatically records a branching AI-assisted coding history and allows developers to manipulate the graph to compare, merge, and revisit prior collaborative AI programming states. Our user study with 20 participants revealed that EvoGraph addressed developers' challenges identified in our preliminary study while imposing lower cognitive load. Participants also found the graph-based representation supported safe exploration, efficient iteration, and reflection on AI-generated changes. Our work highlights design opportunities for tools to help developers make sense of and act on their problem-solving progress in the emerging AI-mediated programming context.